A learning rule for very simple universal approximators consisting of a single layer of perceptrons.

Peter Auer Harald Burgsteiner Wolfgang Maass A learning rule for very simple universal approximators consisting of a single layer of perceptrons. 786-795 2008 21 Neural Networks 5 http://dx.doi.org/10.1016/j.neunet.2007.12.036 db/journals/nn/nn21.html#AuerBM08